Pedestrian detection is a crucial task in intelligent transportation systems, which can be applied in autonomous vehicles and traffic scene video surveillance systems. The past few years have witnessed much progress on the research of pedestrian detection methods, especially through the successful use of the deep learning based techniques. However, occlusion and large scale variation remain the challenging issues for pedestrian detection. In this work, we propose a Part-Aware Multi-Scale Fully Convolutional Network (PAMS-FCN) to tackle these difficulties. Specifically, we present a part-aware Region-of-Interest (RoI) pooling module to mine body parts with different responses, and select the part with the strongest response via voting. As such, a partially visible pedestrian instance can receive a high detection confidence score, making it less likely to become a missing detection. This module operates in parallel with an instance RoI pooling module to combine local parts and global context information. To handle vast scale variation, we construct a fully convolutional network in which multi-scale feature maps are generated efficiently, and small-scale and large-scale pedestrians are detected separately. By integrating these structures, the proposed detector achieves the state-of-the-art performance on the Caltech, KITTI, INRIA and ETH pedestrian detection datasets.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Part-Aware Multi-Scale Fully Convolutional Network for Pedestrian Detection


    Contributors:
    Yang, Peiyu (author) / Zhang, Guofeng (author) / Wang, Lu (author) / Xu, Lisheng (author) / Deng, Qingxu (author) / Yang, Ming-Hsuan (author)


    Publication date :

    2021-02-01


    Size :

    4445196 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Temporal-Aware Convolutional Network for First-Person View Pedestrian Trajectory Prediction

    Liu, Yanran / Meng, Qingyu / Xie, Hongnan et al. | IEEE | 2024


    Fast pedestrian detection using scale-aware pooling [10806-142]

    British Library Conference Proceedings | 2018


    Multi-label convolutional neural network based pedestrian attribute classification

    Zhu, Jianqing / Liao, Shengcai / Lei, Zhen et al. | British Library Online Contents | 2017


    Multi-label convolutional neural network based pedestrian attribute classification

    Zhu, Jianqing / Liao, Shengcai / Lei, Zhen et al. | British Library Online Contents | 2017


    Pedestrian Detection with Convolutional Neural Networks

    Szarvas, M. / Yoshizawa, A. / Yamamoto, M. et al. | British Library Conference Proceedings | 2005